1
Polly Huang, NTU EE Artificial Intelligence 1
Introduction to Computer Science
Polly HuangNTU EEhttp://homepage.ntu.edu.tw/[email protected]
Polly Huang, NTU EE Artificial Intelligence 2
Chapter 11
Artificial Intelligence
2
Polly Huang, NTU EE Artificial Intelligence 3
Chapter 11: Artificial Intelligence®11.1 Intelligence and Machines®11.2 Understanding Images®11.3 Reasoning®11.5 Artificial Neural Networks®11.4 Other Areas of Research®11.6 Robotics®11.7 Considering the Consequences
Polly Huang, NTU EE Artificial Intelligence 4
Computer vs. Human® Machine
® Performs precisely defined tasks with speed and accuracy
® Not gifted with common sense
® Human® Capable of understanding and reasoning® More likely to understand the results and
determine what to do next® Not gifted with complex computations
3
Polly Huang, NTU EE Artificial Intelligence 5
Humanlike Computer®The ideal hybrid
®Continue without human intervention when faced with unforeseen situations
®Possess or simulate the ability to reason®Psychologists and their models may be
helpful
Polly Huang, NTU EE Artificial Intelligence 6
Intelligent Agents
®Agent®Device that responds to stimuli from its
environment® Sensors: to receive stimuli® Actuators: to react
®The goal of artificial intelligence®To build agents that behave intelligently
4
Polly Huang, NTU EE Artificial Intelligence 7
Related Fields
PhilosophyArtificialIntelligence
ComputerScience Linguistics
Psychology
BiologyMathematics
Polly Huang, NTU EE Artificial Intelligence 8
AI Research Approaches
® Performance oriented® Researcher tries to maximize the performance of
the agents® Just do it
® Exhaustive search, probabilistic deduction® Computer scientists approach
® Simulation oriented® Researcher tries to understand how the agents
produce responses.® Wait, let me figure what’s going on first
® Heuristic search, classification® Psychologists approach
5
Polly Huang, NTU EE Artificial Intelligence 9
The Eight Puzzle Problem
Polly Huang, NTU EE Artificial Intelligence 10
Puzzle-Solving Machine
Sensor
Actuator
6
Polly Huang, NTU EE Artificial Intelligence 11
Issues Involved®Sensor – Camera
®Understanding the images (11.2)®Finding a solution (11.3)
®Actuator®Based on the solution®Move arms to slide the tiles (Robotics 11.6)
Polly Huang, NTU EE Artificial Intelligence 12
Levels of Intelligence: Not Really Intelligent®Weak AI
®1. Reflex® Actions are fixed and predetermined
®2. Context aware® Actions affected by knowledge of the
environment® Context information
7
Polly Huang, NTU EE Artificial Intelligence 13
Levels of Intelligence:Trying to be Really Intelligent®Strong AI
®3. Goal seeking® Search for a solution ® Key: efficient searching
®4. Learning® Deduce from experience® Key: identifying majority
Polly Huang, NTU EE Artificial Intelligence 14
Turing Test
®Proposed by Alan Turing in 1950®Benchmark for progress in artificial
intelligence®Human interrogator communicates with
test subject by typewriter®Can the human interrogator distinguish
whether the test subject is human or machine?
8
Polly Huang, NTU EE Artificial Intelligence 15
Chapter 11: Artificial Intelligence®11.1 Intelligence and Machines®11.2 Understanding Images®11.3 Reasoning®11.5 Artificial Neural Networks®11.4 Other Areas of Research®11.6 Robotics®11.7 Considering the Consequences
Polly Huang, NTU EE Artificial Intelligence 16
Understanding ImagesComputer Vision
® Template matching® Compare two bitmaps® Ex. recognizing well-formed characters
® Image processing® Consider characters by the common shape® Ex. recognizing hand-written characters
® Edge enhancement® Region finding® Smoothing
® Image analysis® Guess what partial, obstructed objects are® Ex. recognizing what the image means
9
Polly Huang, NTU EE Artificial Intelligence 17
Production Systems
® Capturing common characteristics of reasoning problems
1. Collection of states® Start or initial state® Goal state
2. Collection of productions® Rules or moves ® Each production may have preconditions
3. Control system® Production to apply next
Polly Huang, NTU EE Artificial Intelligence 18
Applications®Playing games
®8 Puzzles, chess®Drawing logical conclusions from given
facts®Reasoning
10
Polly Huang, NTU EE Artificial Intelligence 19
Ex. 8 Puzzle
Polly Huang, NTU EE Artificial Intelligence 20
Ex. Deductive Reasoning
11
Polly Huang, NTU EE Artificial Intelligence 21
Control System® Search tree
® Record of state transitions explored while searching for a goal state
® Searching for goal® Searches the state graph to find a path from the
start node to the goal® Strategies
® Root: start state® Children: states reachable by applying one
production® Walking up the tree from the goal
Polly Huang, NTU EE Artificial Intelligence 22
An Unsolved Eight Puzzle
12
Polly Huang, NTU EE Artificial Intelligence 23
Breadth-First Search Tree
Polly Huang, NTU EE Artificial Intelligence 24
Production Stack
13
Polly Huang, NTU EE Artificial Intelligence 25
Quiz Time!
Polly Huang, NTU EE Artificial Intelligence 26
Types of Searches®Blind
®Breadth-first search®Depth-first search
®Heuristics®Proximity to goal
14
Polly Huang, NTU EE Artificial Intelligence 27
Heuristic Search
Polly Huang, NTU EE Artificial Intelligence 28
Good Heuristics®Easier to compute than a complete
solution®Provide a reasonable estimate of
proximity to a goal
15
Polly Huang, NTU EE Artificial Intelligence 29
Heuristic Search Algorithm
Polly Huang, NTU EE Artificial Intelligence 30
Heuristic Search: Beginning
16
Polly Huang, NTU EE Artificial Intelligence 31
Heuristic Search: 2 passes
Polly Huang, NTU EE Artificial Intelligence 32
Heuristic Search: 3 Passes
17
Polly Huang, NTU EE Artificial Intelligence 33
Heuristic Search: Completion
Polly Huang, NTU EE Artificial Intelligence 34
Quiz Time!
18
Polly Huang, NTU EE Artificial Intelligence 35
Chapter 11: Artificial Intelligence®11.1 Intelligence and Machines®11.2 Understanding Images®11.3 Reasoning®11.5 Artificial Neural Networks®11.4 Other Areas of Research®11.6 Robotics®11.7 Considering the Consequences
Polly Huang, NTU EE Artificial Intelligence 36
Neural Networks
®Artificial Neuron® Input multiplied by a weighting factor®Output
® 1 if sum of inputs exceeds a threshold value® 0 if otherwise.
®Network is programmed by adjusting weights/threshold using feedback from examples.
19
Polly Huang, NTU EE Artificial Intelligence 37
A Biological Neuron
Polly Huang, NTU EE Artificial Intelligence 38
Neuron as Processing Unit
20
Polly Huang, NTU EE Artificial Intelligence 39
An Example
Polly Huang, NTU EE Artificial Intelligence 40
One Network, Two Programs
21
Polly Huang, NTU EE Artificial Intelligence 41
Uppercase C and T
Polly Huang, NTU EE Artificial Intelligence 42
Various Orientations
22
Polly Huang, NTU EE Artificial Intelligence 43
Character Recognition
Polly Huang, NTU EE Artificial Intelligence 44
1st Level Processing Units® One processing unit per 9 cells
® Center cell weight = 2® Other cell weight = -1
® Input value per cell® 1, if highlighted® 0, otherwise
® Threshold 0.5
® Only when center square is highlighted and one or less other cells also highlighted, the output will be 1
23
Polly Huang, NTU EE Artificial Intelligence 45
2nd Level Processing Units ® All outputs from the 1st level ® Weight 1® Threshold 0.5
® The final output will be 1 (character T) when at least one output from the 1st levelprocessing unit is 1
® The final output will be 0 (character C) when no output from the 1st level processing unit is 1
Polly Huang, NTU EE Artificial Intelligence 46
The Letter C
24
Polly Huang, NTU EE Artificial Intelligence 47
The Letter T
Polly Huang, NTU EE Artificial Intelligence 48
Associative Memory
®Associative memory®The retrieval of information relevant to the
information at hand®Application of neural network
®Given a partial pattern®Transition themselves to a completed
pattern.
25
Polly Huang, NTU EE Artificial Intelligence 49
Example Neural Network1. Circle –
Processing unit
2. Number in circle – Threshold
3. Line – Output to be the input of the connected processing unit
4. Number on line –Weight of input
Polly Huang, NTU EE Artificial Intelligence 50
Stablization
26
Polly Huang, NTU EE Artificial Intelligence 51
Chapter 11: Artificial Intelligence®11.1 Intelligence and Machines®11.2 Understanding Images®11.3 Reasoning®11.5 Artificial Neural Networks®11.4 Other Areas of Research®11.5 Robotics®11.7 Considering the Consequences
Polly Huang, NTU EE Artificial Intelligence 52
Genetic Algorithms
® Simulate genetic processes to evolve algorithms® Start with an initial population of “partial solutions.”® Graft together parts of the best performers to form
a new population.® Periodically make slight modifications to some
members of the current population.® Repeat until a satisfactory solution is obtained.
27
Polly Huang, NTU EE Artificial Intelligence 53
Crossing Two Strategies
Polly Huang, NTU EE Artificial Intelligence 54
Neural Networks
®Artificial Neuron® Input multiplied by a weighting factor®Output
® 1 if sum of inputs exceeds a threshold value® 0 if otherwise.
®Network is programmed by adjusting weights/threshold using feedback from examples.
28
Polly Huang, NTU EE Artificial Intelligence 55
ApplicationConfiguring Neural Networks
Polly Huang, NTU EE Artificial Intelligence 56
Language Processing
®Syntactic analysis®Semantic analysis®Contextual analysis
® Information retrieval® Information extraction (knowledge
representation)®Semantic net
29
Polly Huang, NTU EE Artificial Intelligence 57
A Semantic Net
Polly Huang, NTU EE Artificial Intelligence 58
Robotics
®Before®A field within mechanical and electrical
engineering®Now
®A much wider range of activities®Robocup competition®Evolutionary robotics
30
Polly Huang, NTU EE Artificial Intelligence 59
Expert systems
®Software package to assist humans in situations where expert knowledge is required
®Example: medical diagnosis®Often similar to a production system®Blackboard model
®Whatever the expert says®Several problem-solving systems share a
common data area
Polly Huang, NTU EE Artificial Intelligence 60
Debates
® When should a computer’s decision be trusted over a human’s?
® If a computer can do a job better than a human, when should a human do the job anyway?
® What would be the social impact if computer “intelligence” surpasses that of many humans?
31
Polly Huang, NTU EE Artificial Intelligence 61
Questions?